CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tapd-story-specify

迭代执行流水线技术澄清与规范生成阶段。通过 tech-lead 分两段执行: 技术澄清段审查需求并产出澄清结论,specify 段生成 spec.md。 两段共享统一的 questions.md 代问循环机制——遇到无法自答的问题以 blocked_on_questions 退出,由外部代问后以 answer 指令重入继续。 支持 blocked_on_questions 代问重入与跨阶段回退重入。

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tapd-story-pipeline/tapd-story-specify/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered orchestration document: deterministic state-machine tables, explicit status handling, a validation checklist, and bounded retry/escalation rules, with heavy domain material appropriately split into reference files. The only gaps are minor — duplicated stage-handling tables between §2/§3 and a couple of ambiguously or externally located references.

DimensionReasoningScore

Conciseness

Dense and operational throughout — no explanations of concepts Claude already knows — with only minor redundancy: the 回传处理 table and the "若 attempts > 1,附上 iteration-patches/attempt-${attempts}.md 摘要" line are duplicated between §2 and §3.

4 / 5

Actionability

Exact file paths (${WORKDIR}/req.md, questions.md, spec.md), status codes (ok / blocked_on_questions / fail / spec_insufficient), round limits (3 / 5), template section anchors (§2.0, §2.1, §3, §1.2) and snapshot naming (spec.md.prev-attempt${N}-round${R}) make it executable; formats for last_failure and history records are left unspecified.

4 / 5

Workflow Clarity

Five clearly sequenced stages with an exhaustive re-entry decision table (§1), an explicit quality-validation checklist with pass criteria and failure routing (§4), and complete feedback loops — blocked→answer resume, fail→回退重入 outside the attempt, and round-limit escalation per §1.2.

5 / 5

Progressive Disclosure

The orchestration overview correctly keeps the 287-line clarification guide and 134-line template in references/ (both exist and match their cited roles), and references are one level deep with stated purposes; however `state-mutation-guide.md` is cited without a path prefix and most referenced templates live in the parent bundle, unverifiable from this skill's directory.

4 / 5

Total

17

/

20

Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys clearly and concretely what the skill does — a two-stage tech-clarification and spec-generation pipeline stage with a shared proxy-question loop — using mechanism-level terms. It completely lacks "when to use" trigger guidance and leans on internal jargon, so intent-based matching by a caller may miss it.

Suggestions

Add an explicit trigger clause equivalent to 'Use when...' (e.g., 当 pipeline 主编排在 phase=initialized 且 req.md 就绪、需要产出技术澄清结论与 spec.md 时调起本阶段), naming who invokes it and under what conditions.

Include natural terms and synonyms a caller would actually use — 技术评审, 技术方案澄清, spec 撰写/生成, 进入开发前的技术把关 — alongside the pipeline-internal terms.

Trim mechanism detail (blocked_on_questions/answer 重入细节) from the description and keep it at the capability + trigger level, since the body already documents the re-entry protocol.

DimensionReasoningScore

Specificity

Names several concrete actions — "技术澄清段审查需求并产出澄清结论", "specify 段生成 spec.md", "以 blocked_on_questions 退出…以 answer 指令重入继续" — but coverage of the stage's full behavior (validation, state update, rollback) is incomplete.

4 / 5

Completeness

The "what" is clear — a two-stage technical clarification and spec-generation pipeline stage sharing a questions.md proxy-question loop — but there is no "Use when..." or equivalent trigger guidance; when to invoke it is only weakly implied by "迭代执行流水线…阶段".

3 / 5

Trigger Term Quality

Relevant domain keywords appear (技术澄清, 规范生成, spec.md), but there are no synonyms or variations (技术评审, spec 撰写, 技术把关) and much of the text is internal mechanism jargon (blocked_on_questions, 代问循环) rather than phrases a caller would naturally say.

3 / 5

Distinctiveness Conflict Risk

The niche is distinct — a specific pipeline stage with unique questions.md proxy-loop mechanics — but without explicit trigger boundaries it has minor overlap risk with sibling requirement-clarification or spec-generation sub-skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

TencentBlueKing/bk-bcs

Path

.agents/skills/tapd-story-pipeline/tapd-story-specify/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.